Long-context LLMs Struggle with Long In-context Learning
Paper
•
2404.02060
•
Published
•
35
Papers - University - University of Waterloo
-
-
Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks
Paper • 2211.12588 • Published • 3 -
StructLM: Towards Building Generalist Models for Structured Knowledge Grounding
Paper • 2402.16671 • Published • 26 -
Chinese Tiny LLM: Pretraining a Chinese-Centric Large Language Model
Paper • 2404.04167 • Published • 12 -
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Paper • 2404.07972 • Published • 43 -
Hydragen: High-Throughput LLM Inference with Shared Prefixes
Paper • 2402.05099 • Published • 18 -
McEval: Massively Multilingual Code Evaluation
Paper • 2406.07436 • Published • 39